mlsanityData to 14 Oct 2026

3D Pose Nowcasting: Forecast the Future to Improve the Present

arXiv 2308.12914 ↗First posted 24 Aug 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Technologies to enable safe and effective collaboration and coexistence between humans and robots have gained significant importance in the last few years. A critical component useful for realizing this collaborative paradigm is the understanding of human and robot 3D poses using non-invasive systems. Therefore, in this paper, we propose a novel vision-based system leveraging depth data to accurately establish the 3D locations of skeleton joints. Specifically, we introduce the concept of Pose Nowcasting, denoting the capability of the proposed system to enhance its current pose estimation accuracy by jointly learning to forecast future poses. The experimental evaluation is conducted on two different datasets, providing accurate and real-time performance and confirming the validity of the proposed method on both the robotic and human scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 63 references that are in the map. First posted on arXiv 24 Aug 2023.

Builds on

31 of 63 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  3. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  4. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  5. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  6. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 207
  7. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  8. 2018QuaterNet: A Quaternion-based Recurrent Model for Human Motioncited by 109
  9. 2017V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Mapcited by 102
  10. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  11. 2020Spatial Temporal Transformer Network for Skeleton-based Action Recognitioncited by 77
  12. 2018Action-Agnostic Human Pose Forecastingcited by 56
19 more
  1. 2019A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Imagecited by 56
  2. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  3. 2021Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objectscited by 50
  4. 2019Camera-to-Robot Pose Estimation from a Single Imagecited by 48
  5. 2022mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensorscited by 38
  6. 2018Predicting Future Instance Segmentation by Forecasting Convolutional Featurescited by 37
  7. 2021Single-view robot pose and joint angle estimation via render & comparecited by 33
  8. 2022Motron: Multimodal Probabilistic Human Motion Forecastingcited by 30
  9. 2019Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervisioncited by 27
  10. 2022Pose Forecasting in Industrial Human-Robot Collaborationcited by 25
  11. 2021DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoderscited by 23
  12. 2018CRAVES: Controlling Robotic Arm with a Vision-based Economic Systemcited by 18
  13. 2017Forecasting Human Dynamics from Static Imagescited by 17
  14. 2015Kinect Range Sensing: Structured-Light versus Time-of-Flight Kinectcited by 16
  15. 2017Human Pose Forecasting via Deep Markov Modelscited by 16
  16. 2020Forecasting Characteristic 3D Poses of Human Actionscited by 16
  17. 2017Towards Good Practices for Deep 3D Hand Pose Estimationcited by 11
  18. 2021NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actionscited by 11
  19. 2022Semi-Perspective Decoupled Heatmaps for 3D Robot Pose Estimation from Depth Mapscited by 6

Built on by

Not cited yet.